Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

Model weights
Compare

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

Modalities
In / Out Price
$0.065 / $0.75per 1M
Context
262K
Released
Feb 25, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen: Qwen3.5-35B-A3B (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen3.5 35B A3B (Reasoning) Intelligence Index19.3
Artificial AnalysisQwen3.5 35B A3B (Reasoning) GPQA Diamond84.5%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) HLE21.0%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) IFBench72.5%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) τ²-Bench Telecom89.2%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) AA-LCR72.0%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) CritPt0.9%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) Terminal-Bench Hard26.5%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) AA-Omniscience Accuracy20.1%
Artificial AnalysisQwen3.5 35B A3B (Reasoning) AA-Omniscience Non-Hallucination Rate14.6%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) Intelligence Index15.1
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) Coding Index37.0
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) GPQA Diamond81.9%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) HLE13.4%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) IFBench44.5%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) τ²-Bench Telecom86.3%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) AA-LCR63.0%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) τ-Bench Banking4.9%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) GDPval-AA5.4%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) CritPt0.6%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) Terminal-Bench Hard10.6%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) Terminal-Bench 2.140.8%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) AA-Omniscience Accuracy15.7%
Artificial AnalysisQwen3.5 35B A3B (Non-reasoning) AA-Omniscience Non-Hallucination Rate6.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.1500$1.00$0.05000.94s136 tps
99.93%
$0.1625$1.30--0.67s109 tps
99.93%
$0.1400$1.00$0.05000.50s44 tps
99.18%
$0.1500$1.00$0.05000.64s34 tps
100.00%
$0.2400$1.80$0.15000.86s47 tps
93.39%
$0.0650$0.75$0.03251.05s50 tps
99.67%
$0.2250$1.80$0.22501.49s72 tps
95.83%
Throughput
136tok/s

P50, best across providers

Latency
0.50s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchSiliconFlow83.2%--DeepInfra82.7%--Alibaba Cloud Int.83.0%79.7%auto-routing81.2%77.9%Parasail81.6%76.8%
+3 more providers
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.85%

Availability over the last 3 days

Last 72 hours
Availability 99.85%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.87%
Without Routing
97.84%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
2.06Btokens
2.
Favicon for https://github.com/HKUDS/nanobot
nanobot
Ultra-lightweight personal AI agent
1.39Btokens
3.
Favicon for https://docs.all-hands.dev/
OpenHands
AI coding agent that can run commands, browse the web, call APIs
790Mtokens
4.
Favicon for https://github.com/marl
marl commit0 rollouts
new
418Mtokens
5.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
348Mtokens

Frequently asked questions

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

Qwen3.5-35B-A3B costs $0.065/M input tokens and $0.75/M output tokens, with separate rates for Cache Read at $0.0325/M tokens.

Qwen3.5-35B-A3B has a 262,144 token context window. It supports up to 32,768 completion tokens.

Yes. Qwen3.5-35B-A3B accepts tools and tool_choice for function calling on 5 of the 7 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Qwen3.5-35B-A3B accepts text, images, and video as input and returns text.

Qwen3.5-35B-A3B is served by 7 providers on OpenRouter: Darkbloom, DeepInfra, Parasail, Venice, Alibaba Cloud Int., AtlasCloud, and SiliconFlow. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3.5-35B-A3B was released on February 25, 2026.